TASK 1

First of all, let’s find expected frequencies of words.

library(tidyverse)
## Warning: пакет 'tidyverse' был собран под R версии 4.1.3
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.2.1     v dplyr   1.1.2
## v tidyr   1.1.4     v stringr 1.4.0
## v readr   2.1.1     v forcats 0.5.1
## Warning: пакет 'tibble' был собран под R версии 4.1.3
## Warning: пакет 'dplyr' был собран под R версии 4.1.3
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(dplyr)
freq_rnc <- read_tsv("https://raw.githubusercontent.com/LingData2019/LingData/master/data/freq_rnc_ranked.csv")
## Rows: 52138 Columns: 7
## -- Column specification --------------------------------------------------------
## Delimiter: "\t"
## chr (2): Lemma, PoS
## dbl (5): Rank, Freq(ipm), R, D, Doc
## 
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.
freq_rnc
## # A tibble: 52,138 x 7
##     Rank Lemma PoS   `Freq(ipm)`     R     D   Doc
##    <dbl> <chr> <chr>       <dbl> <dbl> <dbl> <dbl>
##  1     1 и     conj       35802.   100    99 37704
##  2     2 в     pr         31374.   100    98 37865
##  3     3 не    part       18028    100    97 33999
##  4     4 на    pr         15867.   100    98 36748
##  5     5 я     spro       12684.   100    95 17116
##  6     6 быть  v          12161.   100    98 34184
##  7     7 он    spro       11791.   100    95 28132
##  8     8 с     pr         11312.   100    99 35700
##  9     9 что   conj        8354    100    98 32419
## 10    10 а     conj        8198    100    97 32332
## # i 52,128 more rows
all_freqs <- freq_rnc$`Freq(ipm)`
all_freqs[1:10]
##  [1] 35801.8 31374.2 18028.0 15867.3 12684.4 12160.7 11791.1 11311.9  8354.0
## [10]  8198.0

Now let’s take out the rows that contain verbs:

## # A tibble: 12,344 x 7
##     Rank Lemma    PoS   `Freq(ipm)`     R     D   Doc
##    <dbl> <chr>    <chr>       <dbl> <dbl> <dbl> <dbl>
##  1     6 быть     v          12161.   100    98 34184
##  2    37 мочь     v           2912.   100    98 25413
##  3    42 сказать  v           2397.   100    94 15426
##  4    58 говорить v           1755    100    96 17120
##  5    61 знать    v           1714.   100    95 13494
##  6    62 стать    v           1622.   100    97 21235
##  7    92 хотеть   v            991.   100    95 12290
##  8    95 идти     v            957.   100    96 13815
##  9   100 иметь    v            907.   100    96 17493
## 10   114 видеть   v            818.   100    96  9914
## # i 12,334 more rows

And now let’s summarize the frequencies of all verbs and divide them into the sum of frequencies of the whole dictionary:

## [1] 158043.6
## [1] 955648.2
## [1] 0.1653784

The null hypothesis will be the following = the probability of verbs in the corpus of verses from 1820s won’t be different from the dictionary. The alternative hypothesis will be the following = the probability of verbs in the corpus of verses from 1820s will be different from the dictionary.

Now let’s open the data set of verses and filter it by decade (we’re interested in 1820s)

## Rows: 364 Columns: 6
## -- Column specification --------------------------------------------------------
## Delimiter: "\t"
## chr (3): UPoS, LineText, Author
## dbl (3): Decade, RhymedNwords, RhymedNsyl
## 
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.
## # A tibble: 364 x 6
##    Decade RhymedNwords RhymedNsyl UPoS  LineText                          Author
##     <dbl>        <dbl>      <dbl> <chr> <chr>                             <chr> 
##  1   1820            1          1 NOUN  «Промчалась туча грозных бед,     В. Г.~
##  2   1820            1          1 NOUN  Вечерний звон, вечерний звон!     И. И.~
##  3   1820            1          1 NOUN  Давно ли жизнию кипела в сердце ~ В. Н.~
##  4   1820            1          1 NOUN  Наш славный Владимир, наш солныш~ П. А.~
##  5   1820            1          1 PRON  Не привлекаю девы я,              А. Ф.~
##  6   1820            1          1 PRON  Сначала жизнь пленяет нас:        Д. В.~
##  7   1820            1          1 PRON  Ты в Петербурге, ты со мной,      А. А.~
##  8   1820            1          2 ADJ   Голов сто, мнений сто; год новый~ А. Г.~
##  9   1820            1          2 ADJ   Девица юная подобна розе нежной,  К. Н.~
## 10   1820            1          2 ADJ   Отчего, мой ангел милый,          И. П.~
## # i 354 more rows
## # A tibble: 87 x 6
##    Decade RhymedNwords RhymedNsyl UPoS  LineText                          Author
##     <dbl>        <dbl>      <dbl> <chr> <chr>                             <chr> 
##  1   1820            1          1 NOUN  «Промчалась туча грозных бед,     В. Г.~
##  2   1820            1          1 NOUN  Вечерний звон, вечерний звон!     И. И.~
##  3   1820            1          1 NOUN  Давно ли жизнию кипела в сердце ~ В. Н.~
##  4   1820            1          1 NOUN  Наш славный Владимир, наш солныш~ П. А.~
##  5   1820            1          1 PRON  Не привлекаю девы я,              А. Ф.~
##  6   1820            1          1 PRON  Сначала жизнь пленяет нас:        Д. В.~
##  7   1820            1          1 PRON  Ты в Петербурге, ты со мной,      А. А.~
##  8   1820            1          2 ADJ   Голов сто, мнений сто; год новый~ А. Г.~
##  9   1820            1          2 ADJ   Девица юная подобна розе нежной,  К. Н.~
## 10   1820            1          2 ADJ   Отчего, мой ангел милый,          И. П.~
## # i 77 more rows

The number of rows for 1820 is the following:

## [1] 87

The number of rows for verbs in 1820s is the following:

## [1] 15

Now let’s count the p-value

## 
##  Exact binomial test
## 
## data:  number_1820s_verbs and number_1820s
## number of successes = 15, number of trials = 87, p-value = 0.885
## alternative hypothesis: true probability of success is not equal to 0.1653784
## 95 percent confidence interval:
##  0.09983452 0.26837791
## sample estimates:
## probability of success 
##              0.1724138

The p-value is too big, so we cannot reject the null hypothesis.

TASK 2

First let’s determine the samples:

## [1] 1 5 4 3 5
## [1]  4 30 20  5 10 50

Here are the means for two samples:

## [1] 3.6
## [1] 19.83333

According to my intuition, the means are significantly different, so I assume that p-value will be noticeably low.

Now let’s run the T-test on two our samples:

## 
##  Welch Two Sample t-test
## 
## data:  sample1 and sample2
## t = -2.2245, df = 5.1061, p-value = 0.07558
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -34.875664   2.408998
## sample estimates:
## mean of x mean of y 
##   3.60000  19.83333

The p-value is higher than 0.05. Here I would rather choose null hypothesis. I would say that the data in these samples is close to random.

Playing with data

## 
##  Welch Two Sample t-test
## 
## data:  sample1_mod_1 and sample2_mod_1
## t = -3.5948, df = 5.1061, p-value = 0.01508
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -44.875664  -7.591002
## sample estimates:
## mean of x mean of y 
##   3.60000  29.83333

Increase of mean difference influences p-value - it is decreasing, which means that the sample is becoming less random. It makes sense, because t-test literally shows the difference between two samples (how random they are).

## 
##  Welch Two Sample t-test
## 
## data:  sample1_mod_2 and sample2_mod_2
## t = -2.3031, df = 5.3336, p-value = 0.06624
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -20.0467040   0.9133706
## sample estimates:
## mean of x mean of y 
##   3.60000  13.16667

Decrease of mean difference influences p-value - it is increasing, which means that the sample is becoming more random. The data is becoming more similar and now it looks like it was taken randomly.

## 
##  Welch Two Sample t-test
## 
## data:  sample1_mod_3 and sample2_mod_3
## t = -1.7901, df = 3.2184, p-value = 0.1651
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -30.955494   8.122161
## sample estimates:
## mean of x mean of y 
##  3.333333 14.750000

Decrease of sample size influences p-value - it is increasing, which means that the sample is becoming more random. The less data we have, the more similar it is, the less differences we can find among the values.

## [1] 3.6
## [1] 19.7
## 
##  Welch Two Sample t-test
## 
## data:  sample1_mod_4 and sample2_mod_4
## t = -3.5017, df = 9.2727, p-value = 0.006404
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -26.454289  -5.745711
## sample estimates:
## mean of x mean of y 
##       3.6      19.7

Here I tried to extend samples while having the same mean. The p-value became noticeably decreased, which means that the sample is becoming less random. The more data we have, the less similar it is, the more differences we can find among the values.

## [1] 3.8
## [1] 19.66667
## 
##  Welch Two Sample t-test
## 
## data:  sample1_mod_5 and sample2_mod_5
## t = -31.663, df = 8.5569, p-value = 3.611e-10
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -17.00927 -14.72407
## sample estimates:
## mean of x mean of y 
##   3.80000  19.66667

Here I tried to decrease sample diversity while having the same mean. The p-value drastically decreased, which means that the more similar data is inside of the samples, the more likely it’s not random.

## [1] 3.6
## [1] 19.66667
## 
##  Welch Two Sample t-test
## 
## data:  sample1_mod_6 and sample2_mod_6
## t = -1.4761, df = 5.4879, p-value = 0.1949
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -43.31412  11.18079
## sample estimates:
## mean of x mean of y 
##   3.60000  19.66667

Here I tried to increase sample diversity while having the same mean. The p-value increased, which means that the less similar data is inside of the samples, the more likely it’s random.

Playing with alternatives

Now let’s run the T-test on two our samples with alternative “less”:

## 
##  Welch Two Sample t-test
## 
## data:  sample1 and sample2
## t = -2.2245, df = 5.1061, p-value = 0.03779
## alternative hypothesis: true difference in means is less than 0
## 95 percent confidence interval:
##       -Inf -1.595627
## sample estimates:
## mean of x mean of y 
##   3.60000  19.83333

Here I would reject null hypothesis and choose alternative one. It makes sense because the mean of the first sample is less than the second one. It means that the drugs shorten the length of illness, which means that the drug seems to be effective. Though, if I’m not mistaken, in medicine way smaller p-values are used.

Now let’s run the T-test on two our samples with alternative “greater”:

## 
##  Welch Two Sample t-test
## 
## data:  sample1 and sample2
## t = -2.2245, df = 5.1061, p-value = 0.9622
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
##  -30.87104       Inf
## sample estimates:
## mean of x mean of y 
##   3.60000  19.83333

Here the p-value is close to 1, which means that no effect is observed. It also makes sense, because the values of the first sample do not spread on the right side of the graph. The results do not mean that the illness is going to last longer for those who use drugs, it only means that it’s not going to last shorter.

Data frames

##    value sample_id
## 1      1         1
## 2      5         1
## 3      4         1
## 4      3         1
## 5      5         1
## 6      4         2
## 7     30         2
## 8     20         2
## 9      5         2
## 10    10         2
## 11    50         2
## 
##  Welch Two Sample t-test
## 
## data:  value by sample_id
## t = -2.2245, df = 5.1061, p-value = 0.07558
## alternative hypothesis: true difference in means between group 1 and group 2 is not equal to 0
## 95 percent confidence interval:
##  -34.875664   2.408998
## sample estimates:
## mean in group 1 mean in group 2 
##         3.60000        19.83333

Task 3

Let’s open the data set.

## New names:
## Rows: 832 Columns: 8
## -- Column specification
## -------------------------------------------------------- Delimiter: "," chr
## (4): Lemma, Participant, Cond, Exponent dbl (4): ...1, LogDurationA,
## LogDurationW, Frequency
## i Use `spec()` to retrieve the full column specification for this data. i
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## * `` -> `...1`
## # A tibble: 832 x 8
##     ...1 LogDurationA LogDurationW Lemma  Participant Cond  Exponent Frequency
##    <dbl>        <dbl>        <dbl> <chr>  <chr>       <chr> <chr>        <dbl>
##  1 11431        -1.32       -0.477 schab  Art_02_S01  slow  t            -6.98
##  2     1        -1.36       -0.360 blas   Art_02_S01  slow  n            -5.74
##  3   136        -1.50       -0.270 schlaf Art_02_S01  slow  en           -4.68
##  4    71        -1.28       -0.377 lahm   Art_02_S01  slow  en           -6.26
##  5 11581        -1.33       -0.447 lahm   Art_02_S01  slow  t            -6.47
##  6    33        -1.41       -0.261 fahnd  Art_02_S01  slow  en           -6.15
##  7   100        -1.29       -0.336 mahn   Art_02_S01  slow  en           -5.81
##  8 16957        -1.18       -0.409 bahn   Art_02_S01  slow  t            -5.76
##  9   127        -1.29       -0.466 schad  Art_02_S01  slow  n            -5.00
## 10   163        -1.47       -0.342 wat    Art_02_S01  slow  n            -6.43
## # i 822 more rows

Here are the histograms:

Slow VS Fast condition

As we know, negative logarithms stand for values less than 1, which means that the lower values are, the faster they’re pronounced. We can see on the graph that shorter segment duration are found for fast condition, while the longer one is found for slow condition. It is both seen on median value as well as on the value distribution.

Here we see the same situation: word duration is shorter in fast speech and longer in slow speech. Also, unsurprisingly, the lengths of words are bigger than segments. It should be noticed, that graphs show a more noticeable difference between different conditions for words, rather than we saw for segments.

Student t-test

Now let’s check our results using Students t-test.

Word duration

  1. Null hypothesis - the values in samples (word duration in slow VS fast condition) are taken randomly (there’s no difference between two samples). Alternative hypothesis - the samples are not random, there’s a difference between them.
## 
##  Welch Two Sample t-test
## 
## data:  dur_word_freq_slow$LogDurationW and dur_word_freq_fast$LogDurationW
## t = 11.562, df = 829.89, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  0.1123477 0.1582922
## sample estimates:
##  mean of x  mean of y 
## -0.4483053 -0.5836253

As we can see, for word duration p-value is extremely low, which means that the difference is significant and the distribution is not random.

Segment duration

  1. Null hypothesis - the values in samples (segment duration in slow VS fast condition) are taken randomly (there’s no difference between two samples). Alternative hypothesis - the samples are not random, there’s a difference between them.
## 
##  Welch Two Sample t-test
## 
## data:  dur_word_freq_slow$LogDurationA and dur_word_freq_fast$LogDurationA
## t = 7.5116, df = 822.67, p-value = 1.523e-13
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  0.08075098 0.13788190
## sample estimates:
## mean of x mean of y 
## -1.628756 -1.738072

For segment duration p-value is also extremely low, though a bit higher than for word duration, which means that the difference is significant and the distribution is not random, though a bit less significant than for word duration.