Total Electron Content (TEC) is the total number of free electrons inside the cylinder with 1m(2) base area. TEC is an important parameter which is used at the ionospheric variability researches. Ionosphere shows variability according to the observing time period of TEC datas (day to day, seasonal), the stations' positions from where datas are obtained (latitude, longitude) and the factors that caused the variability (solar activity, ionospheric storms, travelling ionospheric disturbances). Observing this variability, by statistical methods gives us information about variability characteristics. In this study to examine the distribution of variability among the frequencies power spectral density is took up. To obtain power spectral density estimation, correlogram method is used. Correlogram method is a autocovariance and discrete fourier transform based nonparametric classical spectral estimation method. The data set we used is the Ionolab-TEC values which is obtained by using the Global Positioning System (GPS) signals. The power spectral densities of the TEC values which are obtained between the time 1999-2006 from Olsztyn (20.6699 degrees D, 53.8924 degrees K), Poland and Hailsham (0.3362 degrees D, 50.8673 degrees K), England stations are observed by using correlogram method. The biggest power spectral density is observed at 1/day frequency. The frequency distribution of the power spectral density are also examined for different frequency units (1/day, 1/month).